Inside ASCENT: Exploring a Deep Commonsense Knowledge Base and its Usage in Question Answering
This work addresses the problem of building and utilizing commonsense knowledge bases for AI applications like question answering, but it appears incremental as it builds on prior work (Nguyen et al., WWW 2021) and focuses on demonstration.
The paper presents ASCENT, a fully automated methodology for extracting and consolidating commonsense assertions from web content, which advances traditional triple-based representations by capturing semantic facets and composite concepts. It demonstrates a web portal for exploring ASCENT's construction and its application in question answering, with online resources available.
ASCENT is a fully automated methodology for extracting and consolidating commonsense assertions from web contents (Nguyen et al., WWW 2021). It advances traditional triple-based commonsense knowledge representation by capturing semantic facets like locations and purposes, and composite concepts, i.e., subgroups and related aspects of subjects. In this demo, we present a web portal that allows users to understand its construction process, explore its content, and observe its impact in the use case of question answering. The demo website and an introductory video are both available online.